Back

EDEPS (Early Detection of ExtraPyramidal Symptoms): supervised machine learning models to detect antipsychotics-induced extrapyramidal hand tremor from a mobile device built-in sensors

Wysokinski, A.; Zwierzchowska-Kieszek, A.

2024-12-16 psychiatry and clinical psychology
10.1101/2024.12.16.24319069 medRxiv
Show abstract

IntroductionApproximately 30% of patients treated with antipsychotics develops extrapyramidal side effects, among which hand tremor is not only common, but also significantly impacting daily activities. No tool for remote assessment of hand tremor is available. Materials and methodsWe collected SAS and AIMS scores and digital recordings of health tremor from healthy and schizophrenia patients on antipsychotics. Next, we created and tested a supervised machine learning models for detecting and measuring severity of antipsychotics-induced hand tremor. ResultsWe present model details, accuracy measures (R2 and RMSE for regressors; log loss, AUC, misclassification, rate, accuracy, sensitivity and specificity for classifiers) and analysis of hand tremor spectral analysis. ConclusionsOur model offers a satisfactory accuracy (0.95 to 1.0) and performance, even if only 10 second data is available. Result of the spectral analysis indicate that the dominating frequency of hand tremor in antipsychotics-induced EPS is approximately 5.0 Hz.

Matching journals

The top 10 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.